Outer Step 1. Inner Step 187. Batch Size 48

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5145014,
-    5145019,
-    5145023,
-    5145029,
-    5145033,
-    5145038,
-    5145042,
-    5145046,
-    5145053,
-    5145059
+    5145093,
+    5145098,
+    5145102,
+    5145106,
+    5145110,
+    5145114,
+    5145119,
+    5145125,
+    5145129,
+    5145133
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 177,
+  "inner_step": 187,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ab87a47a7b814e4747b74aed0abab5fff01efc0f6337392516aacbc0d87e85
+oid sha256:97410ca1c222e10339da3803c60ed22902409e5e888493c87ff5063ef3367417
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3992b2cb51d60a0e666f1a76c8aa8c155e2b6893698162109d94d1a0b8cf2a
+oid sha256:36c6a211413092e4b267159d3783beffd6d003cd67bb952c433f0c6781dc9b51
 size 4040701744